© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 33472
    Prev
    Next
    INDEX
    Explanations

    personal expressions of thought and opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANDLE
    -0.16
    ãģ£ãģ
    -0.16
    isman
    -0.14
    .synthetic
    -0.14
    ále
    -0.14
    elper
    -0.14
    unta
    -0.13
    _compat
    -0.13
    spender
    -0.13
    .AddParameter
    -0.13
    POSITIVE LOGITS
     must
    0.60
    must
    0.51
     Must
    0.47
    Must
    0.44
     gotta
    0.39
     MUST
    0.39
    å¿ħé¡»
    0.37
    .Must
    0.31
    .must
    0.30
     å¿ħ
    0.29
    Activations Density 0.042%

    No Known Activations